Discussion of explicit congestion notification's impact on the Internet
 help / color / mirror / Atom feed
From: Jonathan Morton <chromatix99@gmail.com>
To: Dave Taht <dave.taht@gmail.com>
Cc: "David P. Reed" <dpreed@deepplum.com>,
	Bob Briscoe <ietf@bobbriscoe.net>,
	"ecn-sane@lists.bufferbloat.net" <ecn-sane@lists.bufferbloat.net>,
	tsvwg IETF list <tsvwg@ietf.org>
Subject: Re: [Ecn-sane] per-flow scheduling
Date: Thu, 18 Jul 2019 08:30:28 +0300	[thread overview]
Message-ID: <E43F1DF4-09EF-43D6-A8F8-D3612FA33893@gmail.com> (raw)
In-Reply-To: <CAA93jw7sfreeHrRy==cG7zWn2xo=xVAYn0mSzaNhOZ5BwXQhug@mail.gmail.com>

> On 18 Jul, 2019, at 3:20 am, Dave Taht <dave.taht@gmail.com> wrote:
> 
>> What it should do instead is peek the queue and drop until it hits a
>> markable packet, at the very least.
> 
> I didn't say this well. It should drop otherwise markable packets until it
> exits the loop, and then mark the one it delivers from that flow, if it delivers
> one from that flow. That gets rid of all the extra mass ecn creates...

You know, I think I finally understand what you're talking about here.  You want to treat cases where the marking rate exceeds the flow's packet delivery rate as an overload condition justifying a shift to packet drops.

This actually seems like a sane idea.  There is I think one caveat: selecting the Codel 'interval' parameter will now have an increased penalty for getting it wrong, especially on the too-small side.

 - Jonathan Morton


  reply	other threads:[~2019-07-18  5:30 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-19 14:12 Bob Briscoe
2019-06-19 14:20 ` [Ecn-sane] [tsvwg] " Kyle Rose
2019-06-21  6:59 ` [Ecn-sane] " Sebastian Moeller
2019-06-21  9:33   ` Luca Muscariello
2019-06-21 20:37     ` [Ecn-sane] [tsvwg] " Brian E Carpenter
2019-06-22 19:50       ` David P. Reed
2019-06-22 20:47         ` Jonathan Morton
2019-06-22 22:03           ` Luca Muscariello
2019-06-22 22:09           ` David P. Reed
2019-06-22 23:07             ` Jonathan Morton
2019-06-24 18:57               ` David P. Reed
2019-06-24 19:31                 ` Jonathan Morton
2019-06-24 19:50                   ` David P. Reed
2019-06-24 20:14                     ` Jonathan Morton
2019-06-25 21:05                       ` David P. Reed
2019-06-24 21:25                   ` Luca Muscariello
2019-06-26 12:48             ` Sebastian Moeller
2019-06-26 16:31               ` David P. Reed
2019-06-26 16:53                 ` David P. Reed
2019-06-27  7:54                   ` Sebastian Moeller
2019-06-27  7:49                 ` Sebastian Moeller
2019-06-27 20:33                   ` Brian E Carpenter
2019-06-27 21:31                     ` David P. Reed
2019-06-28  7:49                       ` Toke Høiland-Jørgensen
2019-06-27  7:53                 ` Bless, Roland (TM)
2019-06-22 21:10         ` Brian E Carpenter
2019-06-22 22:25           ` David P. Reed
2019-06-22 22:30             ` Luca Muscariello
2019-07-17 21:33 ` [Ecn-sane] " Sebastian Moeller
2019-07-17 22:18   ` David P. Reed
2019-07-17 22:34     ` David P. Reed
2019-07-17 23:23       ` Dave Taht
2019-07-18  0:20         ` Dave Taht
2019-07-18  5:30           ` Jonathan Morton [this message]
2019-07-18 15:02         ` David P. Reed
2019-07-18 16:06           ` Dave Taht
2019-07-18  4:31     ` Jonathan Morton
2019-07-18 15:52       ` David P. Reed
2019-07-18 18:12         ` [Ecn-sane] [tsvwg] " Dave Taht
2019-07-18  5:24     ` [Ecn-sane] " Jonathan Morton
2019-07-22 13:44       ` Bob Briscoe
2019-07-23  5:00         ` Jonathan Morton
2019-07-23 11:35           ` [Ecn-sane] CNQ cheap-nasty-queuing (was per-flow queuing) Luca Muscariello
2019-07-23 20:14           ` [Ecn-sane] per-flow scheduling Bob Briscoe
2019-07-23 22:24             ` Jonathan Morton
2019-07-23 15:12         ` [Ecn-sane] [tsvwg] " Kyle Rose
2019-07-25 19:25           ` Holland, Jake
2019-07-27 15:35             ` Kyle Rose
2019-07-27 19:42               ` Jonathan Morton

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://lists.bufferbloat.net/postorius/lists/ecn-sane.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=E43F1DF4-09EF-43D6-A8F8-D3612FA33893@gmail.com \
    --to=chromatix99@gmail.com \
    --cc=dave.taht@gmail.com \
    --cc=dpreed@deepplum.com \
    --cc=ecn-sane@lists.bufferbloat.net \
    --cc=ietf@bobbriscoe.net \
    --cc=tsvwg@ietf.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox